Triple
T16267870
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Koosah Falls |
E394917
|
entity |
| Predicate | distanceFromSahalieFalls |
P42849
|
FINISHED |
| Object | approximately 0.5 miles downstream |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: approximately 0.5 miles downstream | Statement: [Koosah Falls, distanceFromSahalieFalls, approximately 0.5 miles downstream]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: distanceFromSahalieFalls Context triple: [Koosah Falls, distanceFromSahalieFalls, approximately 0.5 miles downstream]
-
A.
distanceFromFalls
chosen
Indicates the measured distance between a location or object and a specified waterfall or falls.
-
B.
distanceToSaranacLake
Indicates the spatial distance between a given entity and Saranac Lake.
-
C.
distanceFromFortWilliam
Indicates the measured distance between an entity and Fort William.
-
D.
distanceFromBrowseBasin_km
Indicates the distance, measured in kilometers, between an entity and the Browse Basin.
-
E.
distanceFromQuesnel
Indicates the spatial distance between a given entity or location and Quesnel.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69d87f221d8081909b0b2063e7528ba2 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e245c963ec8190b059fecac6248cd9 |
completed | April 17, 2026, 2:38 p.m. |
| PD | Predicate disambiguation | batch_69e219f259e88190bf49d8408c04178e |
completed | April 17, 2026, 11:30 a.m. |
Created at: April 10, 2026, 5:05 a.m.